Adding upstream version 6.1.76.upstream/6.1.76

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

8 files changed, 1557 insertions, 0 deletions

diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic.c b/tools/testing/selftests/kvm/lib/aarch64/gic.c
new file mode 100644
index 000000000..55668631d
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM Generic Interrupt Controller (GIC) support
+ */
+
+#include <errno.h>
+#include <linux/bits.h>
+#include <linux/sizes.h>
+
+#include "kvm_util.h"
+
+#include <gic.h>
+#include "gic_private.h"
+#include "processor.h"
+#include "spinlock.h"
+
+static const struct gic_common_ops *gic_common_ops;
+static struct spinlock gic_lock;
+
+static void gic_cpu_init(unsigned int cpu, void *redist_base)
+{
+	gic_common_ops->gic_cpu_init(cpu, redist_base);
+}
+
+static void
+gic_dist_init(enum gic_type type, unsigned int nr_cpus, void *dist_base)
+{
+	const struct gic_common_ops *gic_ops = NULL;
+
+	spin_lock(&gic_lock);
+
+	/* Distributor initialization is needed only once per VM */
+	if (gic_common_ops) {
+		spin_unlock(&gic_lock);
+		return;
+	}
+
+	if (type == GIC_V3)
+		gic_ops = &gicv3_ops;
+
+	GUEST_ASSERT(gic_ops);
+
+	gic_ops->gic_init(nr_cpus, dist_base);
+	gic_common_ops = gic_ops;
+
+	/* Make sure that the initialized data is visible to all the vCPUs */
+	dsb(sy);
+
+	spin_unlock(&gic_lock);
+}
+
+void gic_init(enum gic_type type, unsigned int nr_cpus,
+		void *dist_base, void *redist_base)
+{
+	uint32_t cpu = guest_get_vcpuid();
+
+	GUEST_ASSERT(type < GIC_TYPE_MAX);
+	GUEST_ASSERT(dist_base);
+	GUEST_ASSERT(redist_base);
+	GUEST_ASSERT(nr_cpus);
+
+	gic_dist_init(type, nr_cpus, dist_base);
+	gic_cpu_init(cpu, redist_base);
+}
+
+void gic_irq_enable(unsigned int intid)
+{
+	GUEST_ASSERT(gic_common_ops);
+	gic_common_ops->gic_irq_enable(intid);
+}
+
+void gic_irq_disable(unsigned int intid)
+{
+	GUEST_ASSERT(gic_common_ops);
+	gic_common_ops->gic_irq_disable(intid);
+}
+
+unsigned int gic_get_and_ack_irq(void)
+{
+	uint64_t irqstat;
+	unsigned int intid;
+
+	GUEST_ASSERT(gic_common_ops);
+
+	irqstat = gic_common_ops->gic_read_iar();
+	intid = irqstat & GENMASK(23, 0);
+
+	return intid;
+}
+
+void gic_set_eoi(unsigned int intid)
+{
+	GUEST_ASSERT(gic_common_ops);
+	gic_common_ops->gic_write_eoir(intid);
+}
+
+void gic_set_dir(unsigned int intid)
+{
+	GUEST_ASSERT(gic_common_ops);
+	gic_common_ops->gic_write_dir(intid);
+}
+
+void gic_set_eoi_split(bool split)
+{
+	GUEST_ASSERT(gic_common_ops);
+	gic_common_ops->gic_set_eoi_split(split);
+}
+
+void gic_set_priority_mask(uint64_t pmr)
+{
+	GUEST_ASSERT(gic_common_ops);
+	gic_common_ops->gic_set_priority_mask(pmr);
+}
+
+void gic_set_priority(unsigned int intid, unsigned int prio)
+{
+	GUEST_ASSERT(gic_common_ops);
+	gic_common_ops->gic_set_priority(intid, prio);
+}
+
+void gic_irq_set_active(unsigned int intid)
+{
+	GUEST_ASSERT(gic_common_ops);
+	gic_common_ops->gic_irq_set_active(intid);
+}
+
+void gic_irq_clear_active(unsigned int intid)
+{
+	GUEST_ASSERT(gic_common_ops);
+	gic_common_ops->gic_irq_clear_active(intid);
+}
+
+bool gic_irq_get_active(unsigned int intid)
+{
+	GUEST_ASSERT(gic_common_ops);
+	return gic_common_ops->gic_irq_get_active(intid);
+}
+
+void gic_irq_set_pending(unsigned int intid)
+{
+	GUEST_ASSERT(gic_common_ops);
+	gic_common_ops->gic_irq_set_pending(intid);
+}
+
+void gic_irq_clear_pending(unsigned int intid)
+{
+	GUEST_ASSERT(gic_common_ops);
+	gic_common_ops->gic_irq_clear_pending(intid);
+}
+
+bool gic_irq_get_pending(unsigned int intid)
+{
+	GUEST_ASSERT(gic_common_ops);
+	return gic_common_ops->gic_irq_get_pending(intid);
+}
+
+void gic_irq_set_config(unsigned int intid, bool is_edge)
+{
+	GUEST_ASSERT(gic_common_ops);
+	gic_common_ops->gic_irq_set_config(intid, is_edge);
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
new file mode 100644
index 000000000..75d07313c
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM Generic Interrupt Controller (GIC) private defines that's only
+ * shared among the GIC library code.
+ */
+
+#ifndef SELFTEST_KVM_GIC_PRIVATE_H
+#define SELFTEST_KVM_GIC_PRIVATE_H
+
+struct gic_common_ops {
+	void (*gic_init)(unsigned int nr_cpus, void *dist_base);
+	void (*gic_cpu_init)(unsigned int cpu, void *redist_base);
+	void (*gic_irq_enable)(unsigned int intid);
+	void (*gic_irq_disable)(unsigned int intid);
+	uint64_t (*gic_read_iar)(void);
+	void (*gic_write_eoir)(uint32_t irq);
+	void (*gic_write_dir)(uint32_t irq);
+	void (*gic_set_eoi_split)(bool split);
+	void (*gic_set_priority_mask)(uint64_t mask);
+	void (*gic_set_priority)(uint32_t intid, uint32_t prio);
+	void (*gic_irq_set_active)(uint32_t intid);
+	void (*gic_irq_clear_active)(uint32_t intid);
+	bool (*gic_irq_get_active)(uint32_t intid);
+	void (*gic_irq_set_pending)(uint32_t intid);
+	void (*gic_irq_clear_pending)(uint32_t intid);
+	bool (*gic_irq_get_pending)(uint32_t intid);
+	void (*gic_irq_set_config)(uint32_t intid, bool is_edge);
+};
+
+extern const struct gic_common_ops gicv3_ops;
+
+#endif /* SELFTEST_KVM_GIC_PRIVATE_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
new file mode 100644
index 000000000..263bf3ed8
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
@@ -0,0 +1,398 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM Generic Interrupt Controller (GIC) v3 support
+ */
+
+#include <linux/sizes.h>
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "delay.h"
+
+#include "gic_v3.h"
+#include "gic_private.h"
+
+struct gicv3_data {
+	void *dist_base;
+	void *redist_base[GICV3_MAX_CPUS];
+	unsigned int nr_cpus;
+	unsigned int nr_spis;
+};
+
+#define sgi_base_from_redist(redist_base)	(redist_base + SZ_64K)
+#define DIST_BIT				(1U << 31)
+
+enum gicv3_intid_range {
+	SGI_RANGE,
+	PPI_RANGE,
+	SPI_RANGE,
+	INVALID_RANGE,
+};
+
+static struct gicv3_data gicv3_data;
+
+static void gicv3_gicd_wait_for_rwp(void)
+{
+	unsigned int count = 100000; /* 1s */
+
+	while (readl(gicv3_data.dist_base + GICD_CTLR) & GICD_CTLR_RWP) {
+		GUEST_ASSERT(count--);
+		udelay(10);
+	}
+}
+
+static void gicv3_gicr_wait_for_rwp(void *redist_base)
+{
+	unsigned int count = 100000; /* 1s */
+
+	while (readl(redist_base + GICR_CTLR) & GICR_CTLR_RWP) {
+		GUEST_ASSERT(count--);
+		udelay(10);
+	}
+}
+
+static void gicv3_wait_for_rwp(uint32_t cpu_or_dist)
+{
+	if (cpu_or_dist & DIST_BIT)
+		gicv3_gicd_wait_for_rwp();
+	else
+		gicv3_gicr_wait_for_rwp(gicv3_data.redist_base[cpu_or_dist]);
+}
+
+static enum gicv3_intid_range get_intid_range(unsigned int intid)
+{
+	switch (intid) {
+	case 0 ... 15:
+		return SGI_RANGE;
+	case 16 ... 31:
+		return PPI_RANGE;
+	case 32 ... 1019:
+		return SPI_RANGE;
+	}
+
+	/* We should not be reaching here */
+	GUEST_ASSERT(0);
+
+	return INVALID_RANGE;
+}
+
+static uint64_t gicv3_read_iar(void)
+{
+	uint64_t irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1);
+
+	dsb(sy);
+	return irqstat;
+}
+
+static void gicv3_write_eoir(uint32_t irq)
+{
+	write_sysreg_s(irq, SYS_ICC_EOIR1_EL1);
+	isb();
+}
+
+static void gicv3_write_dir(uint32_t irq)
+{
+	write_sysreg_s(irq, SYS_ICC_DIR_EL1);
+	isb();
+}
+
+static void gicv3_set_priority_mask(uint64_t mask)
+{
+	write_sysreg_s(mask, SYS_ICC_PMR_EL1);
+}
+
+static void gicv3_set_eoi_split(bool split)
+{
+	uint32_t val;
+
+	/*
+	 * All other fields are read-only, so no need to read CTLR first. In
+	 * fact, the kernel does the same.
+	 */
+	val = split ? (1U << 1) : 0;
+	write_sysreg_s(val, SYS_ICC_CTLR_EL1);
+	isb();
+}
+
+uint32_t gicv3_reg_readl(uint32_t cpu_or_dist, uint64_t offset)
+{
+	void *base = cpu_or_dist & DIST_BIT ? gicv3_data.dist_base
+		: sgi_base_from_redist(gicv3_data.redist_base[cpu_or_dist]);
+	return readl(base + offset);
+}
+
+void gicv3_reg_writel(uint32_t cpu_or_dist, uint64_t offset, uint32_t reg_val)
+{
+	void *base = cpu_or_dist & DIST_BIT ? gicv3_data.dist_base
+		: sgi_base_from_redist(gicv3_data.redist_base[cpu_or_dist]);
+	writel(reg_val, base + offset);
+}
+
+uint32_t gicv3_getl_fields(uint32_t cpu_or_dist, uint64_t offset, uint32_t mask)
+{
+	return gicv3_reg_readl(cpu_or_dist, offset) & mask;
+}
+
+void gicv3_setl_fields(uint32_t cpu_or_dist, uint64_t offset,
+		uint32_t mask, uint32_t reg_val)
+{
+	uint32_t tmp = gicv3_reg_readl(cpu_or_dist, offset) & ~mask;
+
+	tmp |= (reg_val & mask);
+	gicv3_reg_writel(cpu_or_dist, offset, tmp);
+}
+
+/*
+ * We use a single offset for the distributor and redistributor maps as they
+ * have the same value in both. The only exceptions are registers that only
+ * exist in one and not the other, like GICR_WAKER that doesn't exist in the
+ * distributor map. Such registers are conveniently marked as reserved in the
+ * map that doesn't implement it; like GICR_WAKER's offset of 0x0014 being
+ * marked as "Reserved" in the Distributor map.
+ */
+static void gicv3_access_reg(uint32_t intid, uint64_t offset,
+		uint32_t reg_bits, uint32_t bits_per_field,
+		bool write, uint32_t *val)
+{
+	uint32_t cpu = guest_get_vcpuid();
+	enum gicv3_intid_range intid_range = get_intid_range(intid);
+	uint32_t fields_per_reg, index, mask, shift;
+	uint32_t cpu_or_dist;
+
+	GUEST_ASSERT(bits_per_field <= reg_bits);
+	GUEST_ASSERT(!write || *val < (1U << bits_per_field));
+	/*
+	 * This function does not support 64 bit accesses. Just asserting here
+	 * until we implement readq/writeq.
+	 */
+	GUEST_ASSERT(reg_bits == 32);
+
+	fields_per_reg = reg_bits / bits_per_field;
+	index = intid % fields_per_reg;
+	shift = index * bits_per_field;
+	mask = ((1U << bits_per_field) - 1) << shift;
+
+	/* Set offset to the actual register holding intid's config. */
+	offset += (intid / fields_per_reg) * (reg_bits / 8);
+
+	cpu_or_dist = (intid_range == SPI_RANGE) ? DIST_BIT : cpu;
+
+	if (write)
+		gicv3_setl_fields(cpu_or_dist, offset, mask, *val << shift);
+	*val = gicv3_getl_fields(cpu_or_dist, offset, mask) >> shift;
+}
+
+static void gicv3_write_reg(uint32_t intid, uint64_t offset,
+		uint32_t reg_bits, uint32_t bits_per_field, uint32_t val)
+{
+	gicv3_access_reg(intid, offset, reg_bits,
+			bits_per_field, true, &val);
+}
+
+static uint32_t gicv3_read_reg(uint32_t intid, uint64_t offset,
+		uint32_t reg_bits, uint32_t bits_per_field)
+{
+	uint32_t val;
+
+	gicv3_access_reg(intid, offset, reg_bits,
+			bits_per_field, false, &val);
+	return val;
+}
+
+static void gicv3_set_priority(uint32_t intid, uint32_t prio)
+{
+	gicv3_write_reg(intid, GICD_IPRIORITYR, 32, 8, prio);
+}
+
+/* Sets the intid to be level-sensitive or edge-triggered. */
+static void gicv3_irq_set_config(uint32_t intid, bool is_edge)
+{
+	uint32_t val;
+
+	/* N/A for private interrupts. */
+	GUEST_ASSERT(get_intid_range(intid) == SPI_RANGE);
+	val = is_edge ? 2 : 0;
+	gicv3_write_reg(intid, GICD_ICFGR, 32, 2, val);
+}
+
+static void gicv3_irq_enable(uint32_t intid)
+{
+	bool is_spi = get_intid_range(intid) == SPI_RANGE;
+	uint32_t cpu = guest_get_vcpuid();
+
+	gicv3_write_reg(intid, GICD_ISENABLER, 32, 1, 1);
+	gicv3_wait_for_rwp(is_spi ? DIST_BIT : cpu);
+}
+
+static void gicv3_irq_disable(uint32_t intid)
+{
+	bool is_spi = get_intid_range(intid) == SPI_RANGE;
+	uint32_t cpu = guest_get_vcpuid();
+
+	gicv3_write_reg(intid, GICD_ICENABLER, 32, 1, 1);
+	gicv3_wait_for_rwp(is_spi ? DIST_BIT : cpu);
+}
+
+static void gicv3_irq_set_active(uint32_t intid)
+{
+	gicv3_write_reg(intid, GICD_ISACTIVER, 32, 1, 1);
+}
+
+static void gicv3_irq_clear_active(uint32_t intid)
+{
+	gicv3_write_reg(intid, GICD_ICACTIVER, 32, 1, 1);
+}
+
+static bool gicv3_irq_get_active(uint32_t intid)
+{
+	return gicv3_read_reg(intid, GICD_ISACTIVER, 32, 1);
+}
+
+static void gicv3_irq_set_pending(uint32_t intid)
+{
+	gicv3_write_reg(intid, GICD_ISPENDR, 32, 1, 1);
+}
+
+static void gicv3_irq_clear_pending(uint32_t intid)
+{
+	gicv3_write_reg(intid, GICD_ICPENDR, 32, 1, 1);
+}
+
+static bool gicv3_irq_get_pending(uint32_t intid)
+{
+	return gicv3_read_reg(intid, GICD_ISPENDR, 32, 1);
+}
+
+static void gicv3_enable_redist(void *redist_base)
+{
+	uint32_t val = readl(redist_base + GICR_WAKER);
+	unsigned int count = 100000; /* 1s */
+
+	val &= ~GICR_WAKER_ProcessorSleep;
+	writel(val, redist_base + GICR_WAKER);
+
+	/* Wait until the processor is 'active' */
+	while (readl(redist_base + GICR_WAKER) & GICR_WAKER_ChildrenAsleep) {
+		GUEST_ASSERT(count--);
+		udelay(10);
+	}
+}
+
+static inline void *gicr_base_cpu(void *redist_base, uint32_t cpu)
+{
+	/* Align all the redistributors sequentially */
+	return redist_base + cpu * SZ_64K * 2;
+}
+
+static void gicv3_cpu_init(unsigned int cpu, void *redist_base)
+{
+	void *sgi_base;
+	unsigned int i;
+	void *redist_base_cpu;
+
+	GUEST_ASSERT(cpu < gicv3_data.nr_cpus);
+
+	redist_base_cpu = gicr_base_cpu(redist_base, cpu);
+	sgi_base = sgi_base_from_redist(redist_base_cpu);
+
+	gicv3_enable_redist(redist_base_cpu);
+
+	/*
+	 * Mark all the SGI and PPI interrupts as non-secure Group-1.
+	 * Also, deactivate and disable them.
+	 */
+	writel(~0, sgi_base + GICR_IGROUPR0);
+	writel(~0, sgi_base + GICR_ICACTIVER0);
+	writel(~0, sgi_base + GICR_ICENABLER0);
+
+	/* Set a default priority for all the SGIs and PPIs */
+	for (i = 0; i < 32; i += 4)
+		writel(GICD_INT_DEF_PRI_X4,
+				sgi_base + GICR_IPRIORITYR0 + i);
+
+	gicv3_gicr_wait_for_rwp(redist_base_cpu);
+
+	/* Enable the GIC system register (ICC_*) access */
+	write_sysreg_s(read_sysreg_s(SYS_ICC_SRE_EL1) | ICC_SRE_EL1_SRE,
+			SYS_ICC_SRE_EL1);
+
+	/* Set a default priority threshold */
+	write_sysreg_s(ICC_PMR_DEF_PRIO, SYS_ICC_PMR_EL1);
+
+	/* Enable non-secure Group-1 interrupts */
+	write_sysreg_s(ICC_IGRPEN1_EL1_ENABLE, SYS_ICC_GRPEN1_EL1);
+
+	gicv3_data.redist_base[cpu] = redist_base_cpu;
+}
+
+static void gicv3_dist_init(void)
+{
+	void *dist_base = gicv3_data.dist_base;
+	unsigned int i;
+
+	/* Disable the distributor until we set things up */
+	writel(0, dist_base + GICD_CTLR);
+	gicv3_gicd_wait_for_rwp();
+
+	/*
+	 * Mark all the SPI interrupts as non-secure Group-1.
+	 * Also, deactivate and disable them.
+	 */
+	for (i = 32; i < gicv3_data.nr_spis; i += 32) {
+		writel(~0, dist_base + GICD_IGROUPR + i / 8);
+		writel(~0, dist_base + GICD_ICACTIVER + i / 8);
+		writel(~0, dist_base + GICD_ICENABLER + i / 8);
+	}
+
+	/* Set a default priority for all the SPIs */
+	for (i = 32; i < gicv3_data.nr_spis; i += 4)
+		writel(GICD_INT_DEF_PRI_X4,
+				dist_base + GICD_IPRIORITYR + i);
+
+	/* Wait for the settings to sync-in */
+	gicv3_gicd_wait_for_rwp();
+
+	/* Finally, enable the distributor globally with ARE */
+	writel(GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A |
+			GICD_CTLR_ENABLE_G1, dist_base + GICD_CTLR);
+	gicv3_gicd_wait_for_rwp();
+}
+
+static void gicv3_init(unsigned int nr_cpus, void *dist_base)
+{
+	GUEST_ASSERT(nr_cpus <= GICV3_MAX_CPUS);
+
+	gicv3_data.nr_cpus = nr_cpus;
+	gicv3_data.dist_base = dist_base;
+	gicv3_data.nr_spis = GICD_TYPER_SPIS(
+				readl(gicv3_data.dist_base + GICD_TYPER));
+	if (gicv3_data.nr_spis > 1020)
+		gicv3_data.nr_spis = 1020;
+
+	/*
+	 * Initialize only the distributor for now.
+	 * The redistributor and CPU interfaces are initialized
+	 * later for every PE.
+	 */
+	gicv3_dist_init();
+}
+
+const struct gic_common_ops gicv3_ops = {
+	.gic_init = gicv3_init,
+	.gic_cpu_init = gicv3_cpu_init,
+	.gic_irq_enable = gicv3_irq_enable,
+	.gic_irq_disable = gicv3_irq_disable,
+	.gic_read_iar = gicv3_read_iar,
+	.gic_write_eoir = gicv3_write_eoir,
+	.gic_write_dir = gicv3_write_dir,
+	.gic_set_priority_mask = gicv3_set_priority_mask,
+	.gic_set_eoi_split = gicv3_set_eoi_split,
+	.gic_set_priority = gicv3_set_priority,
+	.gic_irq_set_active = gicv3_irq_set_active,
+	.gic_irq_clear_active = gicv3_irq_clear_active,
+	.gic_irq_get_active = gicv3_irq_get_active,
+	.gic_irq_set_pending = gicv3_irq_set_pending,
+	.gic_irq_clear_pending = gicv3_irq_clear_pending,
+	.gic_irq_get_pending = gicv3_irq_get_pending,
+	.gic_irq_set_config = gicv3_irq_set_config,
+};
diff --git a/tools/testing/selftests/kvm/lib/aarch64/handlers.S b/tools/testing/selftests/kvm/lib/aarch64/handlers.S
new file mode 100644
index 000000000..0e443eadf
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/handlers.S
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+.macro save_registers
+	add	sp, sp, #-16 * 17
+
+	stp	x0, x1, [sp, #16 * 0]
+	stp	x2, x3, [sp, #16 * 1]
+	stp	x4, x5, [sp, #16 * 2]
+	stp	x6, x7, [sp, #16 * 3]
+	stp	x8, x9, [sp, #16 * 4]
+	stp	x10, x11, [sp, #16 * 5]
+	stp	x12, x13, [sp, #16 * 6]
+	stp	x14, x15, [sp, #16 * 7]
+	stp	x16, x17, [sp, #16 * 8]
+	stp	x18, x19, [sp, #16 * 9]
+	stp	x20, x21, [sp, #16 * 10]
+	stp	x22, x23, [sp, #16 * 11]
+	stp	x24, x25, [sp, #16 * 12]
+	stp	x26, x27, [sp, #16 * 13]
+	stp	x28, x29, [sp, #16 * 14]
+
+	/*
+	 * This stores sp_el1 into ex_regs.sp so exception handlers can "look"
+	 * at it. It will _not_ be used to restore the sp on return from the
+	 * exception so handlers can not update it.
+	 */
+	add	x1, sp, #16 * 17
+	stp	x30, x1, [sp, #16 * 15] /* x30, SP */
+
+	mrs	x1, elr_el1
+	mrs	x2, spsr_el1
+	stp	x1, x2, [sp, #16 * 16] /* PC, PSTATE */
+.endm
+
+.macro restore_registers
+	ldp	x1, x2, [sp, #16 * 16] /* PC, PSTATE */
+	msr	elr_el1, x1
+	msr	spsr_el1, x2
+
+	/* sp is not restored */
+	ldp	x30, xzr, [sp, #16 * 15] /* x30, SP */
+
+	ldp	x28, x29, [sp, #16 * 14]
+	ldp	x26, x27, [sp, #16 * 13]
+	ldp	x24, x25, [sp, #16 * 12]
+	ldp	x22, x23, [sp, #16 * 11]
+	ldp	x20, x21, [sp, #16 * 10]
+	ldp	x18, x19, [sp, #16 * 9]
+	ldp	x16, x17, [sp, #16 * 8]
+	ldp	x14, x15, [sp, #16 * 7]
+	ldp	x12, x13, [sp, #16 * 6]
+	ldp	x10, x11, [sp, #16 * 5]
+	ldp	x8, x9, [sp, #16 * 4]
+	ldp	x6, x7, [sp, #16 * 3]
+	ldp	x4, x5, [sp, #16 * 2]
+	ldp	x2, x3, [sp, #16 * 1]
+	ldp	x0, x1, [sp, #16 * 0]
+
+	add	sp, sp, #16 * 17
+
+	eret
+.endm
+
+.pushsection ".entry.text", "ax"
+.balign 0x800
+.global vectors
+vectors:
+.popsection
+
+.set	vector, 0
+
+/*
+ * Build an exception handler for vector and append a jump to it into
+ * vectors (while making sure that it's 0x80 aligned).
+ */
+.macro HANDLER, label
+handler_\label:
+	save_registers
+	mov	x0, sp
+	mov	x1, #vector
+	bl	route_exception
+	restore_registers
+
+.pushsection ".entry.text", "ax"
+.balign 0x80
+	b	handler_\label
+.popsection
+
+.set	vector, vector + 1
+.endm
+
+.macro HANDLER_INVALID
+.pushsection ".entry.text", "ax"
+.balign 0x80
+/* This will abort so no need to save and restore registers. */
+	mov	x0, #vector
+	mov	x1, #0 /* ec */
+	mov	x2, #0 /* valid_ec */
+	b	kvm_exit_unexpected_exception
+.popsection
+
+.set	vector, vector + 1
+.endm
+
+/*
+ * Caution: be sure to not add anything between the declaration of vectors
+ * above and these macro calls that will build the vectors table below it.
+ */
+	HANDLER_INVALID                         // Synchronous EL1t
+	HANDLER_INVALID                         // IRQ EL1t
+	HANDLER_INVALID                         // FIQ EL1t
+	HANDLER_INVALID                         // Error EL1t
+
+	HANDLER	el1h_sync                       // Synchronous EL1h
+	HANDLER	el1h_irq                        // IRQ EL1h
+	HANDLER el1h_fiq                        // FIQ EL1h
+	HANDLER	el1h_error                      // Error EL1h
+
+	HANDLER	el0_sync_64                     // Synchronous 64-bit EL0
+	HANDLER	el0_irq_64                      // IRQ 64-bit EL0
+	HANDLER	el0_fiq_64                      // FIQ 64-bit EL0
+	HANDLER	el0_error_64                    // Error 64-bit EL0
+
+	HANDLER	el0_sync_32                     // Synchronous 32-bit EL0
+	HANDLER	el0_irq_32                      // IRQ 32-bit EL0
+	HANDLER	el0_fiq_32                      // FIQ 32-bit EL0
+	HANDLER	el0_error_32                    // Error 32-bit EL0
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
new file mode 100644
index 000000000..6f5551368
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -0,0 +1,530 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AArch64 code
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+
+#include <linux/compiler.h>
+#include <assert.h>
+
+#include "guest_modes.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+#define DEFAULT_ARM64_GUEST_STACK_VADDR_MIN	0xac0000
+
+static vm_vaddr_t exception_handlers;
+
+static uint64_t page_align(struct kvm_vm *vm, uint64_t v)
+{
+	return (v + vm->page_size) & ~(vm->page_size - 1);
+}
+
+static uint64_t pgd_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	unsigned int shift = (vm->pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift;
+	uint64_t mask = (1UL << (vm->va_bits - shift)) - 1;
+
+	return (gva >> shift) & mask;
+}
+
+static uint64_t pud_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	unsigned int shift = 2 * (vm->page_shift - 3) + vm->page_shift;
+	uint64_t mask = (1UL << (vm->page_shift - 3)) - 1;
+
+	TEST_ASSERT(vm->pgtable_levels == 4,
+		"Mode %d does not have 4 page table levels", vm->mode);
+
+	return (gva >> shift) & mask;
+}
+
+static uint64_t pmd_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	unsigned int shift = (vm->page_shift - 3) + vm->page_shift;
+	uint64_t mask = (1UL << (vm->page_shift - 3)) - 1;
+
+	TEST_ASSERT(vm->pgtable_levels >= 3,
+		"Mode %d does not have >= 3 page table levels", vm->mode);
+
+	return (gva >> shift) & mask;
+}
+
+static uint64_t pte_index(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	uint64_t mask = (1UL << (vm->page_shift - 3)) - 1;
+	return (gva >> vm->page_shift) & mask;
+}
+
+static uint64_t pte_addr(struct kvm_vm *vm, uint64_t entry)
+{
+	uint64_t mask = ((1UL << (vm->va_bits - vm->page_shift)) - 1) << vm->page_shift;
+	return entry & mask;
+}
+
+static uint64_t ptrs_per_pgd(struct kvm_vm *vm)
+{
+	unsigned int shift = (vm->pgtable_levels - 1) * (vm->page_shift - 3) + vm->page_shift;
+	return 1 << (vm->va_bits - shift);
+}
+
+static uint64_t __maybe_unused ptrs_per_pte(struct kvm_vm *vm)
+{
+	return 1 << (vm->page_shift - 3);
+}
+
+void virt_arch_pgd_alloc(struct kvm_vm *vm)
+{
+	if (!vm->pgd_created) {
+		vm_paddr_t paddr = vm_phy_pages_alloc(vm,
+			page_align(vm, ptrs_per_pgd(vm) * 8) / vm->page_size,
+			KVM_GUEST_PAGE_TABLE_MIN_PADDR, 0);
+		vm->pgd = paddr;
+		vm->pgd_created = true;
+	}
+}
+
+static void _virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+			 uint64_t flags)
+{
+	uint8_t attr_idx = flags & 7;
+	uint64_t *ptep;
+
+	TEST_ASSERT((vaddr % vm->page_size) == 0,
+		"Virtual address not on page boundary,\n"
+		"  vaddr: 0x%lx vm->page_size: 0x%x", vaddr, vm->page_size);
+	TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
+		(vaddr >> vm->page_shift)),
+		"Invalid virtual address, vaddr: 0x%lx", vaddr);
+	TEST_ASSERT((paddr % vm->page_size) == 0,
+		"Physical address not on page boundary,\n"
+		"  paddr: 0x%lx vm->page_size: 0x%x", paddr, vm->page_size);
+	TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
+		"Physical address beyond beyond maximum supported,\n"
+		"  paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+		paddr, vm->max_gfn, vm->page_size);
+
+	ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, vaddr) * 8;
+	if (!*ptep)
+		*ptep = vm_alloc_page_table(vm) | 3;
+
+	switch (vm->pgtable_levels) {
+	case 4:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, vaddr) * 8;
+		if (!*ptep)
+			*ptep = vm_alloc_page_table(vm) | 3;
+		/* fall through */
+	case 3:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, vaddr) * 8;
+		if (!*ptep)
+			*ptep = vm_alloc_page_table(vm) | 3;
+		/* fall through */
+	case 2:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, vaddr) * 8;
+		break;
+	default:
+		TEST_FAIL("Page table levels must be 2, 3, or 4");
+	}
+
+	*ptep = paddr | 3;
+	*ptep |= (attr_idx << 2) | (1 << 10) /* Access Flag */;
+}
+
+void virt_arch_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
+{
+	uint64_t attr_idx = 4; /* NORMAL (See DEFAULT_MAIR_EL1) */
+
+	_virt_pg_map(vm, vaddr, paddr, attr_idx);
+}
+
+vm_paddr_t addr_arch_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+	uint64_t *ptep;
+
+	if (!vm->pgd_created)
+		goto unmapped_gva;
+
+	ptep = addr_gpa2hva(vm, vm->pgd) + pgd_index(vm, gva) * 8;
+	if (!ptep)
+		goto unmapped_gva;
+
+	switch (vm->pgtable_levels) {
+	case 4:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pud_index(vm, gva) * 8;
+		if (!ptep)
+			goto unmapped_gva;
+		/* fall through */
+	case 3:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pmd_index(vm, gva) * 8;
+		if (!ptep)
+			goto unmapped_gva;
+		/* fall through */
+	case 2:
+		ptep = addr_gpa2hva(vm, pte_addr(vm, *ptep)) + pte_index(vm, gva) * 8;
+		if (!ptep)
+			goto unmapped_gva;
+		break;
+	default:
+		TEST_FAIL("Page table levels must be 2, 3, or 4");
+	}
+
+	return pte_addr(vm, *ptep) + (gva & (vm->page_size - 1));
+
+unmapped_gva:
+	TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva);
+	exit(1);
+}
+
+static void pte_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent, uint64_t page, int level)
+{
+#ifdef DEBUG
+	static const char * const type[] = { "", "pud", "pmd", "pte" };
+	uint64_t pte, *ptep;
+
+	if (level == 4)
+		return;
+
+	for (pte = page; pte < page + ptrs_per_pte(vm) * 8; pte += 8) {
+		ptep = addr_gpa2hva(vm, pte);
+		if (!*ptep)
+			continue;
+		fprintf(stream, "%*s%s: %lx: %lx at %p\n", indent, "", type[level], pte, *ptep, ptep);
+		pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level + 1);
+	}
+#endif
+}
+
+void virt_arch_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
+{
+	int level = 4 - (vm->pgtable_levels - 1);
+	uint64_t pgd, *ptep;
+
+	if (!vm->pgd_created)
+		return;
+
+	for (pgd = vm->pgd; pgd < vm->pgd + ptrs_per_pgd(vm) * 8; pgd += 8) {
+		ptep = addr_gpa2hva(vm, pgd);
+		if (!*ptep)
+			continue;
+		fprintf(stream, "%*spgd: %lx: %lx at %p\n", indent, "", pgd, *ptep, ptep);
+		pte_dump(stream, vm, indent + 1, pte_addr(vm, *ptep), level);
+	}
+}
+
+void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init)
+{
+	struct kvm_vcpu_init default_init = { .target = -1, };
+	struct kvm_vm *vm = vcpu->vm;
+	uint64_t sctlr_el1, tcr_el1;
+
+	if (!init)
+		init = &default_init;
+
+	if (init->target == -1) {
+		struct kvm_vcpu_init preferred;
+		vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &preferred);
+		init->target = preferred.target;
+	}
+
+	vcpu_ioctl(vcpu, KVM_ARM_VCPU_INIT, init);
+
+	/*
+	 * Enable FP/ASIMD to avoid trapping when accessing Q0-Q15
+	 * registers, which the variable argument list macros do.
+	 */
+	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CPACR_EL1), 3 << 20);
+
+	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), &sctlr_el1);
+	vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), &tcr_el1);
+
+	/* Configure base granule size */
+	switch (vm->mode) {
+	case VM_MODE_P52V48_4K:
+		TEST_FAIL("AArch64 does not support 4K sized pages "
+			  "with 52-bit physical address ranges");
+	case VM_MODE_PXXV48_4K:
+		TEST_FAIL("AArch64 does not support 4K sized pages "
+			  "with ANY-bit physical address ranges");
+	case VM_MODE_P52V48_64K:
+	case VM_MODE_P48V48_64K:
+	case VM_MODE_P40V48_64K:
+	case VM_MODE_P36V48_64K:
+		tcr_el1 |= 1ul << 14; /* TG0 = 64KB */
+		break;
+	case VM_MODE_P48V48_16K:
+	case VM_MODE_P40V48_16K:
+	case VM_MODE_P36V48_16K:
+	case VM_MODE_P36V47_16K:
+		tcr_el1 |= 2ul << 14; /* TG0 = 16KB */
+		break;
+	case VM_MODE_P48V48_4K:
+	case VM_MODE_P40V48_4K:
+	case VM_MODE_P36V48_4K:
+		tcr_el1 |= 0ul << 14; /* TG0 = 4KB */
+		break;
+	default:
+		TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
+	}
+
+	/* Configure output size */
+	switch (vm->mode) {
+	case VM_MODE_P52V48_64K:
+		tcr_el1 |= 6ul << 32; /* IPS = 52 bits */
+		break;
+	case VM_MODE_P48V48_4K:
+	case VM_MODE_P48V48_16K:
+	case VM_MODE_P48V48_64K:
+		tcr_el1 |= 5ul << 32; /* IPS = 48 bits */
+		break;
+	case VM_MODE_P40V48_4K:
+	case VM_MODE_P40V48_16K:
+	case VM_MODE_P40V48_64K:
+		tcr_el1 |= 2ul << 32; /* IPS = 40 bits */
+		break;
+	case VM_MODE_P36V48_4K:
+	case VM_MODE_P36V48_16K:
+	case VM_MODE_P36V48_64K:
+	case VM_MODE_P36V47_16K:
+		tcr_el1 |= 1ul << 32; /* IPS = 36 bits */
+		break;
+	default:
+		TEST_FAIL("Unknown guest mode, mode: 0x%x", vm->mode);
+	}
+
+	sctlr_el1 |= (1 << 0) | (1 << 2) | (1 << 12) /* M | C | I */;
+	/* TCR_EL1 |= IRGN0:WBWA | ORGN0:WBWA | SH0:Inner-Shareable */;
+	tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12);
+	tcr_el1 |= (64 - vm->va_bits) /* T0SZ */;
+
+	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1);
+	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1);
+	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MAIR_EL1), DEFAULT_MAIR_EL1);
+	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TTBR0_EL1), vm->pgd);
+	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TPIDR_EL1), vcpu->id);
+}
+
+void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent)
+{
+	uint64_t pstate, pc;
+
+	vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pstate), &pstate);
+	vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &pc);
+
+	fprintf(stream, "%*spstate: 0x%.16lx pc: 0x%.16lx\n",
+		indent, "", pstate, pc);
+}
+
+struct kvm_vcpu *aarch64_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
+				  struct kvm_vcpu_init *init, void *guest_code)
+{
+	size_t stack_size = vm->page_size == 4096 ?
+					DEFAULT_STACK_PGS * vm->page_size :
+					vm->page_size;
+	uint64_t stack_vaddr = vm_vaddr_alloc(vm, stack_size,
+					      DEFAULT_ARM64_GUEST_STACK_VADDR_MIN);
+	struct kvm_vcpu *vcpu = __vm_vcpu_add(vm, vcpu_id);
+
+	aarch64_vcpu_setup(vcpu, init);
+
+	vcpu_set_reg(vcpu, ARM64_CORE_REG(sp_el1), stack_vaddr + stack_size);
+	vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), (uint64_t)guest_code);
+
+	return vcpu;
+}
+
+struct kvm_vcpu *vm_arch_vcpu_add(struct kvm_vm *vm, uint32_t vcpu_id,
+				  void *guest_code)
+{
+	return aarch64_vcpu_add(vm, vcpu_id, NULL, guest_code);
+}
+
+void vcpu_args_set(struct kvm_vcpu *vcpu, unsigned int num, ...)
+{
+	va_list ap;
+	int i;
+
+	TEST_ASSERT(num >= 1 && num <= 8, "Unsupported number of args,\n"
+		    "  num: %u\n", num);
+
+	va_start(ap, num);
+
+	for (i = 0; i < num; i++) {
+		vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.regs[i]),
+			     va_arg(ap, uint64_t));
+	}
+
+	va_end(ap);
+}
+
+void kvm_exit_unexpected_exception(int vector, uint64_t ec, bool valid_ec)
+{
+	ucall(UCALL_UNHANDLED, 3, vector, ec, valid_ec);
+	while (1)
+		;
+}
+
+void assert_on_unhandled_exception(struct kvm_vcpu *vcpu)
+{
+	struct ucall uc;
+
+	if (get_ucall(vcpu, &uc) != UCALL_UNHANDLED)
+		return;
+
+	if (uc.args[2]) /* valid_ec */ {
+		assert(VECTOR_IS_SYNC(uc.args[0]));
+		TEST_FAIL("Unexpected exception (vector:0x%lx, ec:0x%lx)",
+			  uc.args[0], uc.args[1]);
+	} else {
+		assert(!VECTOR_IS_SYNC(uc.args[0]));
+		TEST_FAIL("Unexpected exception (vector:0x%lx)",
+			  uc.args[0]);
+	}
+}
+
+struct handlers {
+	handler_fn exception_handlers[VECTOR_NUM][ESR_EC_NUM];
+};
+
+void vcpu_init_descriptor_tables(struct kvm_vcpu *vcpu)
+{
+	extern char vectors;
+
+	vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_VBAR_EL1), (uint64_t)&vectors);
+}
+
+void route_exception(struct ex_regs *regs, int vector)
+{
+	struct handlers *handlers = (struct handlers *)exception_handlers;
+	bool valid_ec;
+	int ec = 0;
+
+	switch (vector) {
+	case VECTOR_SYNC_CURRENT:
+	case VECTOR_SYNC_LOWER_64:
+		ec = (read_sysreg(esr_el1) >> ESR_EC_SHIFT) & ESR_EC_MASK;
+		valid_ec = true;
+		break;
+	case VECTOR_IRQ_CURRENT:
+	case VECTOR_IRQ_LOWER_64:
+	case VECTOR_FIQ_CURRENT:
+	case VECTOR_FIQ_LOWER_64:
+	case VECTOR_ERROR_CURRENT:
+	case VECTOR_ERROR_LOWER_64:
+		ec = 0;
+		valid_ec = false;
+		break;
+	default:
+		valid_ec = false;
+		goto unexpected_exception;
+	}
+
+	if (handlers && handlers->exception_handlers[vector][ec])
+		return handlers->exception_handlers[vector][ec](regs);
+
+unexpected_exception:
+	kvm_exit_unexpected_exception(vector, ec, valid_ec);
+}
+
+void vm_init_descriptor_tables(struct kvm_vm *vm)
+{
+	vm->handlers = vm_vaddr_alloc(vm, sizeof(struct handlers),
+			vm->page_size);
+
+	*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
+}
+
+void vm_install_sync_handler(struct kvm_vm *vm, int vector, int ec,
+			 void (*handler)(struct ex_regs *))
+{
+	struct handlers *handlers = addr_gva2hva(vm, vm->handlers);
+
+	assert(VECTOR_IS_SYNC(vector));
+	assert(vector < VECTOR_NUM);
+	assert(ec < ESR_EC_NUM);
+	handlers->exception_handlers[vector][ec] = handler;
+}
+
+void vm_install_exception_handler(struct kvm_vm *vm, int vector,
+			 void (*handler)(struct ex_regs *))
+{
+	struct handlers *handlers = addr_gva2hva(vm, vm->handlers);
+
+	assert(!VECTOR_IS_SYNC(vector));
+	assert(vector < VECTOR_NUM);
+	handlers->exception_handlers[vector][0] = handler;
+}
+
+uint32_t guest_get_vcpuid(void)
+{
+	return read_sysreg(tpidr_el1);
+}
+
+void aarch64_get_supported_page_sizes(uint32_t ipa,
+				      bool *ps4k, bool *ps16k, bool *ps64k)
+{
+	struct kvm_vcpu_init preferred_init;
+	int kvm_fd, vm_fd, vcpu_fd, err;
+	uint64_t val;
+	struct kvm_one_reg reg = {
+		.id	= KVM_ARM64_SYS_REG(SYS_ID_AA64MMFR0_EL1),
+		.addr	= (uint64_t)&val,
+	};
+
+	kvm_fd = open_kvm_dev_path_or_exit();
+	vm_fd = __kvm_ioctl(kvm_fd, KVM_CREATE_VM, (void *)(unsigned long)ipa);
+	TEST_ASSERT(vm_fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VM, vm_fd));
+
+	vcpu_fd = ioctl(vm_fd, KVM_CREATE_VCPU, 0);
+	TEST_ASSERT(vcpu_fd >= 0, KVM_IOCTL_ERROR(KVM_CREATE_VCPU, vcpu_fd));
+
+	err = ioctl(vm_fd, KVM_ARM_PREFERRED_TARGET, &preferred_init);
+	TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_ARM_PREFERRED_TARGET, err));
+	err = ioctl(vcpu_fd, KVM_ARM_VCPU_INIT, &preferred_init);
+	TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_ARM_VCPU_INIT, err));
+
+	err = ioctl(vcpu_fd, KVM_GET_ONE_REG, &reg);
+	TEST_ASSERT(err == 0, KVM_IOCTL_ERROR(KVM_GET_ONE_REG, vcpu_fd));
+
+	*ps4k = ((val >> 28) & 0xf) != 0xf;
+	*ps64k = ((val >> 24) & 0xf) == 0;
+	*ps16k = ((val >> 20) & 0xf) != 0;
+
+	close(vcpu_fd);
+	close(vm_fd);
+	close(kvm_fd);
+}
+
+/*
+ * arm64 doesn't have a true default mode, so start by computing the
+ * available IPA space and page sizes early.
+ */
+void __attribute__((constructor)) init_guest_modes(void)
+{
+       guest_modes_append_default();
+}
+
+void smccc_hvc(uint32_t function_id, uint64_t arg0, uint64_t arg1,
+	       uint64_t arg2, uint64_t arg3, uint64_t arg4, uint64_t arg5,
+	       uint64_t arg6, struct arm_smccc_res *res)
+{
+	asm volatile("mov   w0, %w[function_id]\n"
+		     "mov   x1, %[arg0]\n"
+		     "mov   x2, %[arg1]\n"
+		     "mov   x3, %[arg2]\n"
+		     "mov   x4, %[arg3]\n"
+		     "mov   x5, %[arg4]\n"
+		     "mov   x6, %[arg5]\n"
+		     "mov   x7, %[arg6]\n"
+		     "hvc   #0\n"
+		     "mov   %[res0], x0\n"
+		     "mov   %[res1], x1\n"
+		     "mov   %[res2], x2\n"
+		     "mov   %[res3], x3\n"
+		     : [res0] "=r"(res->a0), [res1] "=r"(res->a1),
+		       [res2] "=r"(res->a2), [res3] "=r"(res->a3)
+		     : [function_id] "r"(function_id), [arg0] "r"(arg0),
+		       [arg1] "r"(arg1), [arg2] "r"(arg2), [arg3] "r"(arg3),
+		       [arg4] "r"(arg4), [arg5] "r"(arg5), [arg6] "r"(arg6)
+		     : "x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7");
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/spinlock.c b/tools/testing/selftests/kvm/lib/aarch64/spinlock.c
new file mode 100644
index 000000000..a076e780b
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/spinlock.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM64 Spinlock support
+ */
+#include <stdint.h>
+
+#include "spinlock.h"
+
+void spin_lock(struct spinlock *lock)
+{
+	int val, res;
+
+	asm volatile(
+	"1:	ldaxr	%w0, [%2]\n"
+	"	cbnz	%w0, 1b\n"
+	"	mov	%w0, #1\n"
+	"	stxr	%w1, %w0, [%2]\n"
+	"	cbnz	%w1, 1b\n"
+	: "=&r" (val), "=&r" (res)
+	: "r" (&lock->v)
+	: "memory");
+}
+
+void spin_unlock(struct spinlock *lock)
+{
+	asm volatile("stlr wzr, [%0]\n"	: : "r" (&lock->v) : "memory");
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
new file mode 100644
index 000000000..ed237b744
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/ucall.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ucall support. A ucall is a "hypercall to userspace".
+ *
+ * Copyright (C) 2018, Red Hat, Inc.
+ */
+#include "kvm_util.h"
+
+static vm_vaddr_t *ucall_exit_mmio_addr;
+
+static bool ucall_mmio_init(struct kvm_vm *vm, vm_paddr_t gpa)
+{
+	if (kvm_userspace_memory_region_find(vm, gpa, gpa + 1))
+		return false;
+
+	virt_pg_map(vm, gpa, gpa);
+
+	ucall_exit_mmio_addr = (vm_vaddr_t *)gpa;
+	sync_global_to_guest(vm, ucall_exit_mmio_addr);
+
+	return true;
+}
+
+void ucall_init(struct kvm_vm *vm, void *arg)
+{
+	vm_paddr_t gpa, start, end, step, offset;
+	unsigned int bits;
+	bool ret;
+
+	if (arg) {
+		gpa = (vm_paddr_t)arg;
+		ret = ucall_mmio_init(vm, gpa);
+		TEST_ASSERT(ret, "Can't set ucall mmio address to %lx", gpa);
+		return;
+	}
+
+	/*
+	 * Find an address within the allowed physical and virtual address
+	 * spaces, that does _not_ have a KVM memory region associated with
+	 * it. Identity mapping an address like this allows the guest to
+	 * access it, but as KVM doesn't know what to do with it, it
+	 * will assume it's something userspace handles and exit with
+	 * KVM_EXIT_MMIO. Well, at least that's how it works for AArch64.
+	 * Here we start with a guess that the addresses around 5/8th
+	 * of the allowed space are unmapped and then work both down and
+	 * up from there in 1/16th allowed space sized steps.
+	 *
+	 * Note, we need to use VA-bits - 1 when calculating the allowed
+	 * virtual address space for an identity mapping because the upper
+	 * half of the virtual address space is the two's complement of the
+	 * lower and won't match physical addresses.
+	 */
+	bits = vm->va_bits - 1;
+	bits = min(vm->pa_bits, bits);
+	end = 1ul << bits;
+	start = end * 5 / 8;
+	step = end / 16;
+	for (offset = 0; offset < end - start; offset += step) {
+		if (ucall_mmio_init(vm, start - offset))
+			return;
+		if (ucall_mmio_init(vm, start + offset))
+			return;
+	}
+	TEST_FAIL("Can't find a ucall mmio address");
+}
+
+void ucall_uninit(struct kvm_vm *vm)
+{
+	ucall_exit_mmio_addr = 0;
+	sync_global_to_guest(vm, ucall_exit_mmio_addr);
+}
+
+void ucall(uint64_t cmd, int nargs, ...)
+{
+	struct ucall uc = {};
+	va_list va;
+	int i;
+
+	WRITE_ONCE(uc.cmd, cmd);
+	nargs = min(nargs, UCALL_MAX_ARGS);
+
+	va_start(va, nargs);
+	for (i = 0; i < nargs; ++i)
+		WRITE_ONCE(uc.args[i], va_arg(va, uint64_t));
+	va_end(va);
+
+	WRITE_ONCE(*ucall_exit_mmio_addr, (vm_vaddr_t)&uc);
+}
+
+uint64_t get_ucall(struct kvm_vcpu *vcpu, struct ucall *uc)
+{
+	struct kvm_run *run = vcpu->run;
+	struct ucall ucall = {};
+
+	if (uc)
+		memset(uc, 0, sizeof(*uc));
+
+	if (run->exit_reason == KVM_EXIT_MMIO &&
+	    run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) {
+		vm_vaddr_t gva;
+
+		TEST_ASSERT(run->mmio.is_write && run->mmio.len == 8,
+			    "Unexpected ucall exit mmio address access");
+		memcpy(&gva, run->mmio.data, sizeof(gva));
+		memcpy(&ucall, addr_gva2hva(vcpu->vm, gva), sizeof(ucall));
+
+		vcpu_run_complete_io(vcpu);
+		if (uc)
+			memcpy(uc, &ucall, sizeof(ucall));
+	}
+
+	return ucall.cmd;
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
new file mode 100644
index 000000000..b5f28d21a
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
@@ -0,0 +1,170 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM Generic Interrupt Controller (GIC) v3 host support
+ */
+
+#include <linux/kvm.h>
+#include <linux/sizes.h>
+#include <asm/kvm_para.h>
+#include <asm/kvm.h>
+
+#include "kvm_util.h"
+#include "vgic.h"
+#include "gic.h"
+#include "gic_v3.h"
+
+/*
+ * vGIC-v3 default host setup
+ *
+ * Input args:
+ *	vm - KVM VM
+ *	nr_vcpus - Number of vCPUs supported by this VM
+ *	gicd_base_gpa - Guest Physical Address of the Distributor region
+ *	gicr_base_gpa - Guest Physical Address of the Redistributor region
+ *
+ * Output args: None
+ *
+ * Return: GIC file-descriptor or negative error code upon failure
+ *
+ * The function creates a vGIC-v3 device and maps the distributor and
+ * redistributor regions of the guest. Since it depends on the number of
+ * vCPUs for the VM, it must be called after all the vCPUs have been created.
+ */
+int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus, uint32_t nr_irqs,
+		uint64_t gicd_base_gpa, uint64_t gicr_base_gpa)
+{
+	int gic_fd;
+	uint64_t redist_attr;
+	struct list_head *iter;
+	unsigned int nr_gic_pages, nr_vcpus_created = 0;
+
+	TEST_ASSERT(nr_vcpus, "Number of vCPUs cannot be empty\n");
+
+	/*
+	 * Make sure that the caller is infact calling this
+	 * function after all the vCPUs are added.
+	 */
+	list_for_each(iter, &vm->vcpus)
+		nr_vcpus_created++;
+	TEST_ASSERT(nr_vcpus == nr_vcpus_created,
+			"Number of vCPUs requested (%u) doesn't match with the ones created for the VM (%u)\n",
+			nr_vcpus, nr_vcpus_created);
+
+	/* Distributor setup */
+	gic_fd = __kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3);
+	if (gic_fd < 0)
+		return gic_fd;
+
+	kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_NR_IRQS, 0, &nr_irqs);
+
+	kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+			    KVM_DEV_ARM_VGIC_CTRL_INIT, NULL);
+
+	kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			    KVM_VGIC_V3_ADDR_TYPE_DIST, &gicd_base_gpa);
+	nr_gic_pages = vm_calc_num_guest_pages(vm->mode, KVM_VGIC_V3_DIST_SIZE);
+	virt_map(vm, gicd_base_gpa, gicd_base_gpa,  nr_gic_pages);
+
+	/* Redistributor setup */
+	redist_attr = REDIST_REGION_ATTR_ADDR(nr_vcpus, gicr_base_gpa, 0, 0);
+	kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+			    KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &redist_attr);
+	nr_gic_pages = vm_calc_num_guest_pages(vm->mode,
+						KVM_VGIC_V3_REDIST_SIZE * nr_vcpus);
+	virt_map(vm, gicr_base_gpa, gicr_base_gpa,  nr_gic_pages);
+
+	kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+			    KVM_DEV_ARM_VGIC_CTRL_INIT, NULL);
+
+	return gic_fd;
+}
+
+/* should only work for level sensitive interrupts */
+int _kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level)
+{
+	uint64_t attr = 32 * (intid / 32);
+	uint64_t index = intid % 32;
+	uint64_t val;
+	int ret;
+
+	ret = __kvm_device_attr_get(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO,
+				    attr, &val);
+	if (ret != 0)
+		return ret;
+
+	val |= 1U << index;
+	ret = __kvm_device_attr_set(gic_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO,
+				    attr, &val);
+	return ret;
+}
+
+void kvm_irq_set_level_info(int gic_fd, uint32_t intid, int level)
+{
+	int ret = _kvm_irq_set_level_info(gic_fd, intid, level);
+
+	TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO, ret));
+}
+
+int _kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level)
+{
+	uint32_t irq = intid & KVM_ARM_IRQ_NUM_MASK;
+
+	TEST_ASSERT(!INTID_IS_SGI(intid), "KVM_IRQ_LINE's interface itself "
+		"doesn't allow injecting SGIs. There's no mask for it.");
+
+	if (INTID_IS_PPI(intid))
+		irq |= KVM_ARM_IRQ_TYPE_PPI << KVM_ARM_IRQ_TYPE_SHIFT;
+	else
+		irq |= KVM_ARM_IRQ_TYPE_SPI << KVM_ARM_IRQ_TYPE_SHIFT;
+
+	return _kvm_irq_line(vm, irq, level);
+}
+
+void kvm_arm_irq_line(struct kvm_vm *vm, uint32_t intid, int level)
+{
+	int ret = _kvm_arm_irq_line(vm, intid, level);
+
+	TEST_ASSERT(!ret, KVM_IOCTL_ERROR(KVM_IRQ_LINE, ret));
+}
+
+static void vgic_poke_irq(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu,
+			  uint64_t reg_off)
+{
+	uint64_t reg = intid / 32;
+	uint64_t index = intid % 32;
+	uint64_t attr = reg_off + reg * 4;
+	uint64_t val;
+	bool intid_is_private = INTID_IS_SGI(intid) || INTID_IS_PPI(intid);
+
+	uint32_t group = intid_is_private ? KVM_DEV_ARM_VGIC_GRP_REDIST_REGS
+					  : KVM_DEV_ARM_VGIC_GRP_DIST_REGS;
+
+	if (intid_is_private) {
+		/* TODO: only vcpu 0 implemented for now. */
+		assert(vcpu->id == 0);
+		attr += SZ_64K;
+	}
+
+	/* Check that the addr part of the attr is within 32 bits. */
+	assert((attr & ~KVM_DEV_ARM_VGIC_OFFSET_MASK) == 0);
+
+	/*
+	 * All calls will succeed, even with invalid intid's, as long as the
+	 * addr part of the attr is within 32 bits (checked above). An invalid
+	 * intid will just make the read/writes point to above the intended
+	 * register space (i.e., ICPENDR after ISPENDR).
+	 */
+	kvm_device_attr_get(gic_fd, group, attr, &val);
+	val |= 1ULL << index;
+	kvm_device_attr_set(gic_fd, group, attr, &val);
+}
+
+void kvm_irq_write_ispendr(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu)
+{
+	vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISPENDR);
+}
+
+void kvm_irq_write_isactiver(int gic_fd, uint32_t intid, struct kvm_vcpu *vcpu)
+{
+	vgic_poke_irq(gic_fd, intid, vcpu, GICD_ISACTIVER);
+}